Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2604.18003 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913047245750272 |
|---|---|
| author | Zhang, Shaowei Qian, Faqiang Chen, Yan Wang, Ziliang An, Kang Dai, Yong Gao, Mengya Wu, Yichao |
| author_facet | Zhang, Shaowei Qian, Faqiang Chen, Yan Wang, Ziliang An, Kang Dai, Yong Gao, Mengya Wu, Yichao |
| contents | Emotion Recognition in Conversation (ERC) has become a fundamental capability for large language models (LLMs) in human-centric interaction. Beyond accurate recognition, coherent emotional expression is also crucial, yet both are limited by the scarcity and static nature of high-quality annotated data. In this work, we propose SELF-EMO, a self-evolution framework grounded in the hypothesis that better emotion prediction leads to more consistent emotional responses. We introduce two auxiliary tasks, emotional understanding and emotional expression, and design a role-based self-play paradigm where the model acts as both an emotion recognizer and a dialogue responder. Through iterative interactions, the model generates diverse conversational trajectories, enabling scalable data generation. To ensure quality, we adopt a data flywheel mechanism that filters candidate predictions and responses using a smoothed IoU-based reward and feeds selected samples back for continuous self-improvement without external supervision. We further develop SELF-GRPO, a reinforcement learning algorithm that stabilizes optimization with multi-label alignment rewards and group-level consistency signals. Experiments on IEMOCAP, MELD, and EmoryNLP show that SELF-EMO achieves state-of-the-art performance, improving accuracy by +6.33% on Qwen3-4B and +8.54% on Qwen3-8B, demonstrating strong effectiveness and generalization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_18003 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SELF-EMO: Emotional Self-Evolution from Recognition to Consistent Expression Zhang, Shaowei Qian, Faqiang Chen, Yan Wang, Ziliang An, Kang Dai, Yong Gao, Mengya Wu, Yichao Artificial Intelligence Emotion Recognition in Conversation (ERC) has become a fundamental capability for large language models (LLMs) in human-centric interaction. Beyond accurate recognition, coherent emotional expression is also crucial, yet both are limited by the scarcity and static nature of high-quality annotated data. In this work, we propose SELF-EMO, a self-evolution framework grounded in the hypothesis that better emotion prediction leads to more consistent emotional responses. We introduce two auxiliary tasks, emotional understanding and emotional expression, and design a role-based self-play paradigm where the model acts as both an emotion recognizer and a dialogue responder. Through iterative interactions, the model generates diverse conversational trajectories, enabling scalable data generation. To ensure quality, we adopt a data flywheel mechanism that filters candidate predictions and responses using a smoothed IoU-based reward and feeds selected samples back for continuous self-improvement without external supervision. We further develop SELF-GRPO, a reinforcement learning algorithm that stabilizes optimization with multi-label alignment rewards and group-level consistency signals. Experiments on IEMOCAP, MELD, and EmoryNLP show that SELF-EMO achieves state-of-the-art performance, improving accuracy by +6.33% on Qwen3-4B and +8.54% on Qwen3-8B, demonstrating strong effectiveness and generalization. |
| title | SELF-EMO: Emotional Self-Evolution from Recognition to Consistent Expression |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2604.18003 |